Refitted cross-validation estimation for high-dimensional subsamples from low-dimension full data
Authors:
Preprint
Abstract
The technique of subsampling has been extensively employed to address the challenges posed by limited computing resources and meet the needs for expedite data analysis. Various subsampling methods have been developed to meet the challenges characterized by a large sample size with a small number of parameters. However, direct applications of these subsampling methods may not be suitable when the dimension is also high and available computing facilities at hand are only able to analyze a subsample of size similar or even smaller than the dimension. In this case, although there is no high-dimensional problem in the full data, the subsample may have a sample size smaller or smaller than the number of parameters, making it a high-dimensional problem. We call this scenario the high-dimensional subsample from low-dimension full data problem. In this paper, we tackle this problem by proposing a novel subsampling-based approach that combines penalty-based dimension reduction and refitted cross-validation. The asymptotic normality of the refitted cross-validation subsample estimator is established, which plays a crucial role in statistical inference. The proposed method demonstrates appealing performance in numerical experiments on simulated data and a real data application.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Subsampling approach for least squares fitting of semi-parametric accelerated failure time models to massive survival dataStatistics and Computing, 2024
- Optimal decorrelated score subsampling for generalized linear models with massive dataScience China Mathematics, 2023
- A review on design inspired subsampling for big dataStatistical Papers, 2023
- Optimal subsampling for parametric accelerated failure time models with massive survival dataStatistics in Medicine, 2022
- Optimal subsample selection for massive logistic regression with distributed dataComputational Statistics, 2021
- Distributed subdata selection for big data via sampling-based approachComputational Statistics & Data Analysis, 2021
- Sampling‐based estimation for massive survival data with additive hazards modelStatistics in Medicine, 2020
- Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators With Massive DataJournal of the American Statistical Association, 2020
- Information-Based Optimal Subdata Selection for Big Data Linear RegressionJournal of the American Statistical Association, 2018
- Optimal Subsampling for Large Sample Logistic RegressionJournal of the American Statistical Association, 2018